Classification of clinical autofluorescence spectra of oral leukoplakia using an artificial neural network: a pilot study.

The performance of an artificial neural network was evaluated as an alternative classification technique of autofluorescence spectra of oral leukoplakia, which may reflect the grade of tissue dysplasia. Twenty-two visible lesions of 21 patients suffering from oral leukoplakia and six locations on normal oral mucosa of volunteers were investigated with autofluorescence spectroscopy (420 nm excitation, 465-650 nm emission). Pre-scaled spectra were combined with the corresponding visual and histopathological classifications in order to train artificial neural networks. A trained network is mapping input spectra to tissue characteristics, which was evaluated using a blind set of spectra. Abnormal tissue could be distinguished from normal tissue by a neural network with a sensitivity of 86% and a specificity of 100%. Also, classifying either homogeneous or non-homogeneous tissue performed reasonably well. Weak or no correlation existed between spectral patterns and verrucous or erosive tissue or the grade of dysplasia, hyperplasia and hyperkeratosis.

[1]  D Zatari,et al.  In vivo liver differentiation by ultrasound using an artificial neural network. , 1994, The Journal of the Acoustical Society of America.

[2]  David K. Stevenson,et al.  Automated classification of tissue by type using real-time spectroscopy , 1998 .

[3]  S. Chow,et al.  Diagnosis of oral cancer by light-induced autofluorescence spectroscopy using double excitation wavelengths. , 1999, Oral oncology.

[4]  Ray L. Somorjai,et al.  Neural network classification of infrared spectra of control and Alzheimer's diseased tissue , 1995, Artif. Intell. Medicine.

[5]  Y Mizuno-Matsumoto,et al.  Occurrences of electroencephalographic (EEG) patterns that resemble epileptiform discharges in background EEG in epileptic patients. , 1997, The International journal of neuroscience.

[6]  G.R. Gindi,et al.  Neural network and conventional classifiers for fluorescence-guided laser angioplasty , 1991, IEEE Transactions on Biomedical Engineering.

[7]  I Itzkan,et al.  Early diagnosis of upper aerodigestive tract cancer by autofluorescence. , 1996, Archives of otolaryngology--head & neck surgery.

[8]  P J Lisboa,et al.  Assessment of statistical and neural networks methods in NMR spectral classification and metabolite selection , 1998, NMR in biomedicine.

[9]  K. Schepman,et al.  Oral leukoplakia: a clinicopathological review. , 1997, Oral oncology.

[10]  J. B. Gomm,et al.  Application of Neural Networks to Modelling and Control , 1993 .

[11]  B. Wilson,et al.  In Vivo Fluorescence Spectroscopy and Imaging for Oncological Applications , 1998, Photochemistry and photobiology.

[12]  Valluru Rao,et al.  C++ neural networks and fuzzy logic , 1993 .

[13]  W Lohmann,et al.  Significance of autofluorescence for the optical demarcation of field cancerisation in the upper aerodigestive tract. , 1997, Acta oto-laryngologica.

[14]  Elie E. Rebeiz,et al.  Diagnostic fluorescence spectroscopy of oral mucosa , 1995, Photonics West.

[15]  B Palcic,et al.  Diagnostic imaging of the larynx: autofluorescence of laryngeal tumours using the helium-cadmium laser , 1995, The Journal of Laryngology & Otology.